Incremental User Identification Across Social Networks Based on User-Guider Similarity Index
Authors: 
Yue Kou, Dong Li, De-Rong Shen, Tie-Zheng Nie, Ge YuAuthors Info & Claims
Yue Kou, Dong Li, De-Rong Shen, Tie-Zheng Nie, Ge YuAuthors Info & ClaimsPages 1086 - 1104
Abstract
Identifying accounts across different online social networks that belong to the same user has attracted extensive attentions. However, existing techniques rely on given user seeds and ignore the dynamic changes of online social networks, which fails to generate high quality identification results. In order to solve this problem, we propose an incremental user identification method based on user-guider similarity index (called CURIOUS), which efficiently identifies users and well captures the changes of user features over time. Specifically, we first construct a novel user-guider similarity index (called USI) to speed up the matching between users. Second we propose a two-phase user identification strategy consisting of USI-based bidirectional user matching and seed-based user matching, which is effective even for incomplete networks. Finally, we propose incremental maintenance for both USI and the identification results, which dynamically captures the instant states of social networks. We conduct experimental studies based on three real-world social networks. The experiments demonstrate the effectiveness and the efficiency of our proposed method in comparison with traditional methods. Compared with the traditional methods, our method improves precision, recall and rank score by an average of 0.19, 0.16 and 0.09 respectively, and reduces the time cost by an average of 81%.
References
[1]
Mu X, Zhu F, Lim E, Xiao J, Wang J, Zhou Z. User identity linkage by latent user space modelling. In Proc. the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Aug. 2016, pp.1775-1784. 10.1145/2939672.2939849.
[2]
Kemp S. Global overview report. Technical Report, Hootsuite, 2022. https://datareportal.com/reports/digital-2022-global-overview-report, Jan. 2022.
[3]
Liu J, Zhang F, Song X, Song Y, Lin C, Hon H. What’s in a name? An unsupervised approach to link users across communities. In Proc. the 6th ACM International Conference on Web Search and Data Mining, Feb. 2013, pp.495-504,.
[4]
Zhang J, Kong X, Yu P S. Transferring heterogeneous links across location-based social networks. In Proc. the 7th ACM International Conference on Web Search and Data Mining, Feb. 2014, pp.303-312,.
[5]
Li Y, Peng Y, Zhang Z, Yin H, and Xu Q Matching user accounts across social networks based on username and display name World Wide Web 2019 22 3 1075-1097
[6]
Liu J, Chai G, Luo Y, Feng J, Tang N. Feature augmentation with reinforcement learning. In Proc. the 38th IEEE International Conference on Data Engineering, May 2022, pp.3360-3372.
[7]
Backstrom L, Leskovec J. Supervised random walks: Predicting and recommending links in social networks. In Proc. the 4th International Conference on Web Search and Web Data Mining, Feb. 2011, pp.635-644,.
[8]
Zafarani R, Liu H. Connecting users across social media sites: A behavioral-modeling approach. In Proc. the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Aug. 2013, pp.41-49.
[9]
Shao J, Wang Y, Gao H, Shen H, Li Y, Cheng X. Locate who you are: Matching geo-location to text for user identity linkage. In Proc. the 30th ACM International Conference on Information and Knowledge Management, Nov. 2021, pp.3413-3417.
[10]
Feng J, Li Y, Yang Z, Zhang M, Wang H, Cao H, and Jin D User identity linkage via co-attentive neural network from heterogeneous mobility data IEEE Trans. Knowl. Data Eng. 2022 34 2 954-968
[11]
Nilizadeh S, Kapadia A, Ahn Y. Community-enhanced de-anonymization of online social networks. In Proc. the 21st ACM SIGSAC Conference on Computer and Communications Security, Nov. 2014, pp.537-548.
[12]
Zhou X, Liang X, Zhang H, and Ma Y Cross-platform identification of anonymous identical users in multiple social media networks IEEE Trans. Knowl. Data Eng. 2016 28 2 411-424
[13]
Singh R, Xu J, and Berger B Global alignment of multiple protein interaction networks with application to functional orthology detection Natl. Acad. Sci. USA 2008 105 35 12763-12768
[14]
Bayati M, Gleich D, Saberi A, Wang Y. Message-passing algorithms for sparse network alignment. ACM Trans. Knowl. Discov. Data, 2013, 7(1): Article No. 3.
[15]
Nassar H, Gleich D. Multimodal network alignment. In Proc. the 17th SIAM International Conference on Data Mining, Apr. 2017, pp.615-623.
[16]
Nassar H, Veldt N, Mohammadi S, Grama A, Gleich D. Low rank spectral network alignment. In Proc. the 27th International World Wide Web Conference, Apr. 2018, pp.619-628.
[17]
Zhou X, Liang X, Du X, and Zhao J Structure based user identification across social networks IEEE Trans. Knowl. Data Eng. 2018 30 6 1178-1191
[18]
Mao X, Wang W, Wu Y, Lan M. Boosting the speed of entity alignment 10 X: Dual attention matching network with normalized hard sample mining. In Proc. the 30th International World Wide Web Conference, Apr. 2021, pp.821-832.
[19]
Chen X, Song X, Peng G, Feng S, Nie L. Adversarial-enhanced hybrid graph network for user identity linkage. In Proc. the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul. 2021, pp.1084-1093.
[20]
Li X, Cao Y, Li Q, Shang Y, Li Y, Liu Y, and Xu G RLINK: Deep reinforcement learning for user identity linkage World Wide Web 2021 24 1 85-103
[21]
Chu X, Fan X, Yao D, Zhu Z, Huang J, Bi J. Cross-network embedding for multi-network alignment. In Proc. the 28th International World Wide Web Conference, May 2019, pp.273-284.
[22]
Chen H, Yin H, Sun X, Chen T, Gabrys B, Musial K. Multi-level graph convolutional networks for cross-platform anchor link prediction. In Proc. the 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Aug. 2020, pp.1503-1511.
[23]
Shun F, Wang G, Xia S, Liu L. Deep multi-granularity graph embedding for user identity linkage across social networks. Knowl. Based Syst., 2020, 193: Article No. 105301.
[24]
Yan J, Yang S, Hancock E. Learning for graph matching and related combinatorial optimization problems. In Proc. the 29th International Joint Conference on Artificial Intelligence, Jan. 2021, pp.4988-4996.
[25]
Zhou F, Zhang K, Xie S, and Luo X Learning to correlate accounts across online social networks: An embedding-based approach INFORMS J. Comput. 2020 32 3 714-729
[26]
Chu X, Fan X, Zhu Z, Bi J. Variational cross-network embedding for anonymized user identity linkage. In Proc. the 30th ACM International Conference on Information and Knowledge Management, Nov. 2021, pp.2955-2959.
[27]
Qian J, Li X, Zhang C, Chen L. De-anonymizing social networks and inferring private attributes using knowledge graphs. In Proc. the 35th Annual IEEE International Conference on Computer Communications, Apr. 2016.
[28]
Heimann M, Shen H, Safavi T, Koutra D. REGAL: Representation learning-based graph alignment. In Proc. the 27th ACM International Conference on Information and Knowledge Management, Oct. 2018, pp.117-126.
[29]
Yasar A, Çatalyürek Ü. An iterative global structure-assisted labeled network aligner. In Proc. the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Aug. 2018, pp.2614-2623.
[30]
Chen B and Chen X MAUIL: Multilevel attribute embedding for semisupervised user identity linkage Inf. Sci. 2022 593 527-545
[31]
Fang Z, Cao Y, Liu Y, Tan J, Guo L, Shang Y. A co-training method for identifying the same person across social networks. In Proc. the 5th IEEE Global Conference on Signal and Information Processing, Nov. 2017, pp.1412-1416.
[32]
Zhong Z, Cao Y, Guo M, Nie Z. CoLink: An unsupervised framework for user identity linkage. In Proc. the 32nd AAAI Conference on Artificial Intelligence, Feb. 2018, pp.5714-5721.
[33]
Xie Z, Zhu R, Zhao K, Liu J, Zhou G, Huang J. A contextual alignment enhanced cross graph attention network for cross-lingual entity alignment. In Proc. the 28th International Conference on Computational Linguistics, Dec. 2020, pp.5918-5928.
[34]
Xiang Y, Zhang Z, Chen J, Chen X, Lin Z, Zheng Y. OntoEA: Ontology-guided entity alignment via joint knowledge graph embedding. In Proc. the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Aug. 2021, pp.1117-1128.
[35]
Heimann M, Lee W, Pan S, Chen K, Koutra D. HashAlign: Hash-based alignment of multiple graphs. In Proc. the 22nd Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining, Jun. 2018, pp.726-739.
[36]
Agarwal P, Fox K, Munagala K, Nath A. Parallel algorithms for constructing range and nearest-neighbor searching data structures. In Proc. the 35th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems, June 26-July 1, 2016, pp.429-440.
[37]
Brown R Building a balanced k-d tree in O(kn log n) time Journal of Computer Graphics Techniques 2015 4 1 50-68
[38]
Yianilos P. Data structures and algorithms for nearest neighbor search in general metric spaces. In Proc. the 4th Annual ACM/SIGACT-SIAM Symposium on Discrete Algorithms, Jan. 1993, pp.311-321.
[39]
Narayanan A, Shmatikov V. De-anonymizing social networks. In Proc. the 30th IEEE Symposium on Security and Privacy, May 2009, pp.173-187.
[40]
Zhang S, Tong H. FINAL: Fast attributed network alignment. In Proc. the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Aug. 2016, pp.1345-1354.
Index Terms
- Incremental User Identification Across Social Networks Based on User-Guider Similarity Index
Index terms have been assigned to the content through auto-classification.
Recommendations
Exploiting similarities of user friendship networks across social networks for user identification
Highlights- All our feature analyses and experiments are conducted on the ground-truth datasets.
- The distributions of features on the positive instances and the negative instances are different.
- The features related to the 1-hop neighbors ...
AbstractUser identification has been attracting considerable attention from academia. Due to the uniqueness and difficulty of faking friendship networks, some friendship-based methods have been presented to improve the identification performance. However,...
MOFC: Network Embedding Based on Multi-Orders Friends Contribution for User Identification
ACAI '23: Proceedings of the 2023 6th International Conference on Algorithms, Computing and Artificial IntelligenceDifferent social networks are independent of each other, and identifying the same person in different social networks is of great significance for cross-network information dissemination and the construction of a complete portrait of users. Existing ...
Fusion of Multi-modal Information of User Profile Across Social Networks for User Identification
Advanced Intelligent Computing Technology and ApplicationsAbstractUser identification across social networks uses various user information to determine whether two accounts from different social networks belong to the same user. The most intuitive method is to use user profiles to solve user identification ...
Comments
Information & Contributors
Information
Published In
© Institute of Computing Technology, Chinese Academy of Sciences 2022.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 01 October 2022
Accepted: 15 September 2022
Received: 15 April 2022
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 04 Oct 2024
Other Metrics
Citations
View Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in